Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.06301 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914639177056256 |
|---|---|
| author | Xu, Shangqing Zhang, Chao |
| author_facet | Xu, Shangqing Zhang, Chao |
| contents | In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem either rely on hard-to-acquire external supervision or require frequent interactions with LLMs, resulting in high costs. We propose a new method called In-Context Reflection (ICR) to overcome these challenges. ICR strategically selects demonstrations to reduce the discrepancy between the LLM's outputs and the actual input-output mappings. Specifically, ICR starts with a random set of initial demonstrations, then iteratively refines it. In each step, it analyzes a pool of candidate examples and identifies the ones most likely to challenge the LLM's current understanding, measured by a new metric called misconfidence. These most confusing examples are then selected to replace the less informative demonstrations in the current set. Our comprehensive evaluation across five diverse datasets encompassing 13 subtasks shows the efficacy of ICR. Compared to existing methods, ICR achieves an average performance boost of 4%, while demonstrating remarkable cross-task generalization capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Misconfidence-based Demonstration Selection for LLM In-Context Learning Xu, Shangqing Zhang, Chao Computation and Language In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem either rely on hard-to-acquire external supervision or require frequent interactions with LLMs, resulting in high costs. We propose a new method called In-Context Reflection (ICR) to overcome these challenges. ICR strategically selects demonstrations to reduce the discrepancy between the LLM's outputs and the actual input-output mappings. Specifically, ICR starts with a random set of initial demonstrations, then iteratively refines it. In each step, it analyzes a pool of candidate examples and identifies the ones most likely to challenge the LLM's current understanding, measured by a new metric called misconfidence. These most confusing examples are then selected to replace the less informative demonstrations in the current set. Our comprehensive evaluation across five diverse datasets encompassing 13 subtasks shows the efficacy of ICR. Compared to existing methods, ICR achieves an average performance boost of 4%, while demonstrating remarkable cross-task generalization capabilities. |
| title | Misconfidence-based Demonstration Selection for LLM In-Context Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.06301 |